© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 14723
    Prev
    Next
    INDEX
    Explanations

    instances of personal relationships and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     various
    -0.08
     Various
    -0.07
    ØŃÙĬ
    -0.07
    awk
    -0.07
    Various
    -0.06
    @nate
    -0.06
     διά
    -0.06
    åħĪçĶŁ
    -0.06
     京
    -0.06
    ichte
    -0.06
    POSITIVE LOGITS
    :
    0.07
     called
    0.07
     whose
    0.07
    yp
    0.06
    *:
    0.06
     very
    0.06
     ë°Ķë¡ľ
    0.06
    ãĥ¼ãĤ¯
    0.06
     Stat
    0.06
    ãĢĤéĤ£
    0.06
    Activations Density 0.047%

    No Known Activations